A method and system for performing real time searches of large alphanumeric data sets including the following steps, combining a cognitive neuromorphic architecture with a neuron based encoding binary filter, wherein building the filter includes encoding input data as a concatenated binary representation, wherein the data becomes a binary value, connecting an axon to a neuron to create a synapse; wherein each binary value includes multiple axons and neurons, determining a weight to each synapse, applying the synaptic weight to the input data to determine an integrated value and determining if the integrated value is greater than or equal to a threshold value.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A method of performing a real time search of large alphanumeric data sets, wherein the search requires less power than traditional processing systems, the method comprising the following steps: combining a cognitive neuromorphic architecture with a neuron based encoding binary filter, wherein building the filter includes: encoding an input data stream as a concatenated binary representation, wherein the input data stream becomes a binary value; duplicating the input data stream; connecting an axon to a neuron to create a synapse for each duplicated data stream; wherein each binary value includes multiple axons and neurons; using one neuron to represent two discrete integrated values; setting a threshold value of the neuron, determining a synaptic weight to each synapse; applying the synaptic weight to the input data to determine an integrated value; and determining if the integrated value is greater than or equal to a threshold value.
2. The method as recited in claim 1 wherein the synaptic weight given to each synapse is 1 for a corresponding value of 1 and negative 1 for the 0 valued inputs.
3. The method as recited in claim 1 wherein the encoding is split into an upper portion and a lower portion, wherein the upper portion is positively weighted and the lower portion is negatively weighted.
4. The method as recited in claim 1 further comprising firing the neuron if the integrated value is greater than or equal to the threshold value.
5. A method of performing a real time search of large alphanumeric data sets with 100% accuracy, wherein the search requires less power than traditional processing systems, the method comprising: combining a cognitive neuromorphic architecture with a neuron based encoding binary filter, wherein building the filter includes: duplicating an input data stream; encoding a binary model in a neuron, wherein the encoding is split into an upper portion and a lower portion; using one neuron to represent two discrete integrated values; setting a threshold value of the neuron, wherein the threshold is set to a number of active synapses in an upper portion; setting synaptic weights for the upper portion and a lower portion; multiplying an input value by the synaptic weight value and summing the totals across the neuron; firing the neuron if the integrated value is greater than or equal to the threshold value.
6. A computing system for real time searches of large alphanumeric datasets comprising; a Cognitive Neuromorphic Architecture (CNA), a neuron based binary encoding filter on the CNA; signals; and a bidirectional neural bus allowing simultaneous storing and processing of information.
7. The system as recited in claim 6 wherein the signals contain numeric or text base sequences embedded within a multiplexed signal of simulated benign, non-target signals in the same frequency range.
8. The system as recited in claim 6 wherein the filter is a discrete valued filter.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
August 17, 2017
March 23, 2021
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.